Product

Extract the context: Sentiment Analysis and Opinion Mining

Ankit Singh
January 16, 2017
3
mins read

Sentiment analysis and opinion mining arrive from the field of study that deals with analyzing emotions, attitude, and sentiments attached with the text. It is one of the most actively researched topics in the areas of Natural Language Processing. The budding growth of sentiment analysis is attributed to the fast-growing social media platforms. These are stacked with brand mentions in the form of reviews, feedback, blog posts, forum discussions and much more. Sentiment analysis is leveraged by almost all the businesses to generate actionable insights and improve overall brand reputation.
Our Sentiment analysis API provides a very accurate analysis of the overall emotion of the text content incorporated from sources like Blogs, Articles, forums, consumer reviews, surveys, twitter etc. You can take demo for free here

How our API works

Sentiment Analysis can be widely applied to reviews and social media for a variety of applications, ranging from marketing to customer service. The following points describe how our API makes the best use of Artificial Intelligence to provide well-grained results:

  • The input data goes through pre- processing where it gets filtered. The punctuations and links are removed and the data becomes more refined and relevant for the system.
  • After pre- processing, each word in the sentence is converted to their corresponding vectors(numeric representation), which are then fed to neural architecture .
  • These vectors are then passed through series of recurrent layers and then to the classification layer which generates the final output (sentiment). The output received is binary that corresponds to positive and negative context.
  • This output is then compared against the actual human tagged labels and then the error is calculated which is finally used to optimize the neural network through backpropagation using SGD. This process goes on until the network is optimized satisfactorily.
  • Based on the input data set of 10 lakh tweets, our architecture has been trained to deliver an accuracy of 88%.

That sums up the procedure to perform sentiment analysis. In order to establish a better understanding of the process, we have taken an example to run on the sentiment analysis API.

Example

Input

The #googlepixel, that's the phone I received yesterday. Innovation at its best. Good job #Google.

Output

{    "sentiment": 0.9850928783416748}

The above JSON output is a score for the sentence "The #googlepixel, that's the phone I received yesterday. Innovation at its best. Good job #Google". This can be used to evaluate the sentiment of the input text. This score will range between 0 and 1 with scores closer to 0 considered to be negative sentiment, scores between 0.4 and 0.5 will be of neutral sentiment while scores closer to 1 will be of positive sentiment.
Based on the above principle, here is how you see the results for the statements you put in for sentiment analysis:

Positive sentiment


Negative sentiments


Neutral


The applications of analyzing the sentiments cannot be overlooked. It can prove a major breakthrough for the complete brand revitalization. The key to running a successful business with the sentiments data is the ability to exploit the unstructured data for actionable insights. The advantages of performing sentiment analysis in business are plenty and overwhelming. Gaining a greater business value with sentiment analysis depends on the accuracy of the tool you use and how well you use it to your advantage. Our API provides highly accurate sentiment classification on social media data (misspellings, emojis, slangs etc.). And, can also be trained on a custom dataset to obtain similar accuracy and performance.

Feedback

Tell us what you think of our Sentiment Analysis API. We are open to suggestions and would love to have your feedback.

Sentiment analysis and opinion mining arrive from the field of study that deals with analyzing emotions, attitude, and sentiments attached with the text. It is one of the most actively researched topics in the areas of Natural Language Processing. The budding growth of sentiment analysis is attributed to the fast-growing social media platforms. These are stacked with brand mentions in the form of reviews, feedback, blog posts, forum discussions and much more. Sentiment analysis is leveraged by almost all the businesses to generate actionable insights and improve overall brand reputation.
Our Sentiment analysis API provides a very accurate analysis of the overall emotion of the text content incorporated from sources like Blogs, Articles, forums, consumer reviews, surveys, twitter etc. You can take demo for free here

How our API works

Sentiment Analysis can be widely applied to reviews and social media for a variety of applications, ranging from marketing to customer service. The following points describe how our API makes the best use of Artificial Intelligence to provide well-grained results:

  • The input data goes through pre- processing where it gets filtered. The punctuations and links are removed and the data becomes more refined and relevant for the system.
  • After pre- processing, each word in the sentence is converted to their corresponding vectors(numeric representation), which are then fed to neural architecture .
  • These vectors are then passed through series of recurrent layers and then to the classification layer which generates the final output (sentiment). The output received is binary that corresponds to positive and negative context.
  • This output is then compared against the actual human tagged labels and then the error is calculated which is finally used to optimize the neural network through backpropagation using SGD. This process goes on until the network is optimized satisfactorily.
  • Based on the input data set of 10 lakh tweets, our architecture has been trained to deliver an accuracy of 88%.

That sums up the procedure to perform sentiment analysis. In order to establish a better understanding of the process, we have taken an example to run on the sentiment analysis API.

Example

Input

The #googlepixel, that's the phone I received yesterday. Innovation at its best. Good job #Google.

Output

{    "sentiment": 0.9850928783416748}

The above JSON output is a score for the sentence "The #googlepixel, that's the phone I received yesterday. Innovation at its best. Good job #Google". This can be used to evaluate the sentiment of the input text. This score will range between 0 and 1 with scores closer to 0 considered to be negative sentiment, scores between 0.4 and 0.5 will be of neutral sentiment while scores closer to 1 will be of positive sentiment.
Based on the above principle, here is how you see the results for the statements you put in for sentiment analysis:

Positive sentiment


Negative sentiments


Neutral


The applications of analyzing the sentiments cannot be overlooked. It can prove a major breakthrough for the complete brand revitalization. The key to running a successful business with the sentiments data is the ability to exploit the unstructured data for actionable insights. The advantages of performing sentiment analysis in business are plenty and overwhelming. Gaining a greater business value with sentiment analysis depends on the accuracy of the tool you use and how well you use it to your advantage. Our API provides highly accurate sentiment classification on social media data (misspellings, emojis, slangs etc.). And, can also be trained on a custom dataset to obtain similar accuracy and performance.

Feedback

Tell us what you think of our Sentiment Analysis API. We are open to suggestions and would love to have your feedback.

No items found.
Ankit Singh
Co-Founder, CTO ParallelDots
Ankit has over seven years of entrepreneurial experience spanning multiple roles across software development and product management with AI at its core. He is currently the co-founder and CTO of ParallelDots. At ParallelDots, he is heading the product and engineering teams to build enterprise grade solutions that is deployed across several Fortune 100 customers.
A graduate from IIT Kharagpur, Ankit worked for Rio Tinto in Australia before moving back to India to start ParallelDots.